{ "epoch": 1.0, "eval_fcm_dpo/beta": 0.0009134606807492673, "eval_logits/chosen": -0.9852490425109863, "eval_logits/rejected": -0.985444188117981, "eval_logps/chosen": -842.9649658203125, "eval_logps/ref_chosen": -79.05104064941406, "eval_logps/ref_rejected": -86.79793548583984, "eval_logps/rejected": -1146.111083984375, "eval_loss": 0.6109764575958252, "eval_margin_dpo/margin_mean": 295.399169921875, "eval_margin_dpo/margin_std": 653.78759765625, "eval_runtime": 39.1532, "eval_samples": 2339, "eval_samples_per_second": 59.74, "eval_steps_per_second": 1.89, "total_flos": 0.0, "train_loss": 1.0910053594522013, "train_runtime": 1869.3984, "train_samples": 43598, "train_samples_per_second": 23.322, "train_steps_per_second": 0.364 }